전자통신동향분석 (Electronics and Telecommunications Trends)

한국전자통신연구원 (Electronics and Telecommunications Research Institute)
권호 표지
DOI QR코드

DOI QR Code

딥러닝 기반 항공안전 이상치 탐지 기술 동향

Research Trends on Deep Learning for Anomaly Detection of Aviation Safety

  • 박노삼 (지능형휴먼트윈연구센터)
  • 발행 : 2021.10.01
PDF 다운로드
⟨ 이전 논문 다음 논문 ⟩

초록

This study reviews application of data-driven anomaly detection techniques to the aviation domain. Recent advances in deep learning have inspired significant anomaly detection research, and numerous methods have been proposed. However, some of these advances have not yet been explored in aviation systems. After briefly introducing aviation safety issues, data-driven anomaly detection models are introduced. Along with traditional statistical and well-established machine learning models, the state-of-the-art deep learning models for anomaly detection are reviewed. In particular, the pros and cons of hybrid techniques that incorporate an existing model and a deep model are reviewed. The characteristics and applications of deep learning models are described, and the possibility of applying deep learning methods in the aviation field is discussed.

키워드

과제정보

본 연구는 국토교통부의 '빅데이터 기반 항공안전관리 기술 개발 및 플랫폼 구축(21BDAS-B158275-02)' 연구의 지원에 의하여 이루어진 연구임.

참고문헌

  1. 국가항공안전프로그램 행정규칙, 국토교통부고시, 2015. 3. 9.
  2. V. Chandola, A. Banerjee, and V. Kumar, "Anomaly detection: A survey," ACM Comput. Surv. vol. 41, 2009, pp. 1-58.
  3. G. Pang et al., "Deep learning for anomaly detection: A review," ACM Comput. Surv. vol. 54, no. 2, article no. 38, 2021.
  4. P. Vincent et al., "Extracting and composing robust features with denoising autoencoders," in Proc. Int. Conf. Mach. Learn. (Helsinki, Finland), July 2008.
  5. M. Welling and P.D. Kingma, "An introduction to variational autoencoders," Found. Trends Mach. Learn. vol. 12, no. 4, 2019, pp. 307-392. https://doi.org/10.1561/2200000056
  6. T. Spinner et al. "Towards an interpretable latent space: An intuitive comparison of autoencoders with variational autoencoders," in Proc. Workshop Vis. AI Explainability, (Berlin, Germany), Oct. 2018.
  7. D.M. Federico et al., "A survey on GANs for anomaly detection," arXiv preprint, CoRR, 2019, arXiv: 1906.11632.
  8. J. Donahue, P. Krahenbuhl, and T. Darrell, "Adversarial feature learning," ICLR, Apr. 2017.
  9. T. Schlegl et al., "Unsupervised anomaly detection with generative adversarial networks to guide marker discovery," arXiv preprint, CoRR, 2017, arXiv: abs/1703.05921.
  10. H. Zenati et al., "Efficient GAN-based anomaly detection," arXiv preprint, CoRR, 2018, arXiv: abs/1802.06222.
  11. S. Akcay, A. Atapour-Abarghouei, and T.P. Breckon, "GANomaly: Semi-supervised anomaly detection via adversarial training," arXiv preprint, CoRR, 2018, arXiv: abs/1805.06725.
  12. B. Scholkopf et al., "Estimating the support of a high-dimentional distribution," Neural Comput. vol. 13, no. 7, 2001, pp. 1443-1471. https://doi.org/10.1162/089976601750264965
  13. R. Chalapathy and S. Chawla, "Deep learning for anomaly detection: A survey," arXiv preprint, CoRR, 2019, arXiv: 1901.03407.
  14. R. Chalapathy, A.K. Menon, and S. Chawla, "Anomaly detection using one-class neural networks," arXiv preprint, CoRR, 2018, arXiv: 1802.06360.
  15. L. Ruff et al., "Deep one-class classification," in Proc. Int. Conf. Mach. Learn. (Stockholm, Sweden), 2018, pp. 4390-4399.
  16. L. Basora, X. Olive, and T. Dubot, "Recent advances in anomaly detection methods applied to aviation," Aerosapce, vol. 6, no. 11, 2018.
  17. S. Das et al., "Multiple kernel learning for heterogeneous anomaly detection: Algorithm and aviation safety case study," in Proc. ACM SIGKDD Int. Conf. Knowl. Discov. Data Min. (Washington, DC, USA), July 2010, pp. 47-56.
  18. L. Li et al., "Anomaly detection in onboard-recorded flight data using cluster analysis," in Proc. IEEE/AIAA Digit. Avionics Syst. Conf. (Seattle, WA, USA), Oct. 2011, pp. 4A41-4A411.
  19. S. Das, B.L. Matthews, and R. Lawrence, "Fleet level anomaly detection of aviation safety data," in Proc. IEEE Conf. Progn. Health Manage. (Denver, CO, USA), June 2011, pp. 1-10.
  20. G. Jia et al., "Verification method for chinese aviation radiotelephony readbacks based on LSTM-RNN," Electron. Lett. vol. 53, 2017, pp. 401-403. https://doi.org/10.1049/el.2016.2877
  21. J. Guimin et al., "Intelligent checking model of Chinese radiotelephony read-backs in civil aviation air traffic control," Chin. J. Aeronaut. vol. 31, 2018, pp. 2280-2289. https://doi.org/10.1016/j.cja.2018.10.001
  22. X. Olive et al., "Detecting controllers' actions in past mode S data by autoencoder-based anomaly detection," in Proc. SESAR Innov. Days (Salzburg, Austria), Dec. 2018.
  23. S. Akerman, E. Habler, and A. Shabtai, "VizADS-B: Analyzing sequences of ADS-B images using explainable convolutional LSTM encoder-decoder to detect cyber attacks," arXiv preprint, CoRR, 2019, arXiv: 1906.07921.
  24. A. Nanduri and L. Sherry, "Anomaly detection in aircraft data using recurrent Neural Networks (RNN)," in Proc. Integrated Commun. Navig. Surveill. (ICNS), (Herndon, VA, USA), Apr. 2016, pp. 5C2-1-5C2-8.
  25. K.K. Reddy et al., "Anomaly detection and fault disambiguation in large flight data: A multi-modal deep auto-encoder approach," in Proc. Annu. Conf. Progn. Health Manage. Soc. (Denver, CO, USA), Oct. 2016.
  26. X. Fu et al., "Aircraft engine fault detection based on grouped convolutional denoising autoencoders," Chin. J. Aeronaut. vol. 32, 2019, pp. 296-307. https://doi.org/10.1016/j.cja.2018.12.011
  27. N. Gugulothu et al., "Predicting remaining useful life using time series embeddings based on recurrent neural networks," arXiv preprint, CoRR, 2018, arXiv: 1709.01073.
  28. R. Zhao et al., "Deep learning and its applications to machine health monitoring," Mech. Syst. Signal Process. vol. 115, 2019, pp. 213-237. https://doi.org/10.1016/j.ymssp.2018.05.050